[go: up one dir, main page]

CN103903303A - Three-dimensional model establishing method and device - Google Patents

Three-dimensional model establishing method and device Download PDF

Info

Publication number
CN103903303A
CN103903303A CN201210581858.2A CN201210581858A CN103903303A CN 103903303 A CN103903303 A CN 103903303A CN 201210581858 A CN201210581858 A CN 201210581858A CN 103903303 A CN103903303 A CN 103903303A
Authority
CN
China
Prior art keywords
dimensional
data
luggage
volume data
isosurface
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201210581858.2A
Other languages
Chinese (zh)
Other versions
CN103903303B (en
Inventor
陈志强
张丽
赵自然
李强
顾建平
黄清萍
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tsinghua University
Nuctech Co Ltd
Original Assignee
Tsinghua University
Nuctech Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tsinghua University, Nuctech Co Ltd filed Critical Tsinghua University
Priority to CN201210581858.2A priority Critical patent/CN103903303B/en
Priority to PCT/CN2013/087662 priority patent/WO2014101600A1/en
Priority to US14/138,447 priority patent/US9557436B2/en
Publication of CN103903303A publication Critical patent/CN103903303A/en
Application granted granted Critical
Publication of CN103903303B publication Critical patent/CN103903303B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V5/00—Prospecting or detecting by the use of ionising radiation, e.g. of natural or induced radioactivity
    • G01V5/20—Detecting prohibited goods, e.g. weapons, explosives, hazardous substances, contraband or smuggled objects
    • G01V5/22—Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays
    • G01V5/226—Active interrogation, i.e. by irradiating objects or goods using external radiation sources, e.g. using gamma rays or cosmic rays using tomography
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10072—Tomographic images
    • G06T2207/10081—Computed x-ray tomography [CT]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30112—Baggage; Luggage; Suitcase
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/05—Recognition of patterns representing particular kinds of hidden objects, e.g. weapons, explosives, drugs

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Geometry (AREA)
  • Computer Graphics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Geophysics (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Analysing Materials By The Use Of Radiation (AREA)
  • General Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Health & Medical Sciences (AREA)
  • Radiology & Medical Imaging (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Image Processing (AREA)

Abstract

公开了一种创建物体的三维模型的方法和设备。该方法包括步骤：利用CT成像系统获取被检查行李的断层数据；对断层数据进行插值，生成被检查行李的三维体数据；对被检查行李的三维体数据进行无监督分割，得到多个分割的区域；对多个分割的区域进行等值面提取，得到相应的等值面；对等值面进行三维表面分割，形成被检查行李中各个物体的三维模型。利用上述方案，能够较为准确地建立被检查行李中物体的三维模型，从而为后续的形状特征提取和安全检查提供较好的基础，从而减少漏检。

A method and apparatus for creating a three-dimensional model of an object are disclosed. The method comprises the steps of: using a CT imaging system to acquire tomographic data of checked luggage; interpolating the tomographic data to generate three-dimensional volume data of checked luggage; performing unsupervised segmentation on the three-dimensional volume data of checked luggage to obtain multiple divided area; perform isosurface extraction on multiple segmented areas to obtain the corresponding isosurface; perform three-dimensional surface segmentation on the isosurface to form a three-dimensional model of each object in the checked luggage. Using the above solution, the three-dimensional model of the object in the checked baggage can be established more accurately, thereby providing a better basis for subsequent shape feature extraction and security inspection, thereby reducing missed inspections.

Description

Three-dimensional model creation method and equipment
Technical field
The present invention relates to a kind of safety inspection to object, be specifically related to three-dimensional model creation method and equipment.
Background technology
Perspective imaging is the important means in safety check field, typical case's application process is: equipment is had an X-rayed scanning imaging to luggage and articles, and figure inspection person is through sentencing figure, manual mark suspicion object area, and semantic description is made in region, as " lighter ", " one bottle of wine " etc.This process too relies on human factor, occurs with minimum probability at real danger, figure inspection person experience is limited, tired etc. that factor affects under, can cause undetectedly, cause serious consequence.
The exemplary means addressing this problem is take automatic auxiliary detection as main, take increase equipment and safety inspector alternately as auxiliary.Although automatically detecting is Main Means, effect is unsatisfactory.Its typical technology can not fully meet application demand as explosive detection, high density warning etc.Trace it to its cause, that technical conditions are limit on the one hand, as the overlapping object aliasing that causes of perspective in DEDR (Dual Energy Digital Radiography), the research of Ye Shi educational circles is less on the other hand, and newer technology needs due to new detection algorithm support as DECT (Dual Energy Computed Tomography).
DECT is the advantage technology addressing this problem, it is by DR, CT technical development, in obtaining scanning thing three-dimensional structure information, can obtain effective atomic number and the equivalent electron density of interior of articles, therefore possess the condition of carrying out three-dimensional data understanding.But existing goal in research is the target detection of certain certain objects often, and main Density-Dependent, atomic number information, the understanding to " object " information lacked.
Summary of the invention
In order more exactly inspected object to be carried out to safety inspection.Three-dimensional model creation method and equipment have been proposed.
In one aspect of the invention, provide a kind of in CT imaging system, create be examined luggage in the method for three-dimensional model of object, comprise step: utilize described CT imaging system to obtain the layer data that is examined luggage; Described layer data is carried out to interpolation, be examined the three-dimensional data of luggage described in generation; The described three-dimensional data that is examined luggage is carried out without supervised segmentation, obtain multiple regions of cutting apart; Contour surface extraction is carried out in described multiple regions of cutting apart, obtain corresponding contour surface; Described contour surface is carried out to three-dimensional surface and cut apart, be examined the three-dimensional model of each object in luggage described in formation.
In another aspect of this invention, provide a kind of in CT imaging system, create be examined luggage in the equipment of three-dimensional model of object, comprising: utilize described CT imaging system to obtain the device of the layer data that is examined luggage; Described layer data is carried out to interpolation, be examined the device of the three-dimensional data of luggage described in generation; The described three-dimensional data that is examined luggage is carried out without supervised segmentation, obtain the device in multiple regions of cutting apart; Contour surface extraction is carried out in described multiple regions of cutting apart, obtain the device of corresponding contour surface; Described contour surface is carried out to three-dimensional surface and cut apart, to be examined the device of the three-dimensional model of each object in luggage described in forming.
Utilize such scheme, can set up comparatively exactly the three-dimensional model that is examined object in luggage, thereby for follow-up Shape Feature Extraction and safety inspection provide good basis, thereby reduce undetected.
Accompanying drawing explanation
Accompanying drawing has below shown the embodiment of this technology.These drawings and embodiments provide some embodiment of this technology in the mode of non-limiting, non exhaustive property, wherein:
Fig. 1 is according to the structural representation of the CT system of the embodiment of the present invention;
Fig. 2 is according to the structural representation of the computer data processor of the embodiment of the present invention;
Fig. 3 is according to the structural representation of the controller of the embodiment of the present invention;
Fig. 4 describes the schematic diagram that does depth projection from View1, View2, tri-visual angles of View3;
Fig. 5 is the process flow diagram of describing according to the method in CT imaging system, inspected object being checked;
Fig. 6 describes the process flow diagram that shows according to another embodiment of the present invention the method for object in CT imaging system;
Fig. 7 be describe in CT imaging system, create luggage according to another embodiment of the present invention in the process flow diagram of method of three-dimensional model of object;
Embodiment
To describe specific embodiments of the invention below in detail, it should be noted that the embodiments described herein, only for illustrating, is not limited to the present invention.In the following description, in order to provide thorough understanding of the present invention, a large amount of specific detail have been set forth.But, it is evident that for those of ordinary skills: needn't adopt these specific detail to carry out the present invention.In other examples, for fear of obscuring the present invention, do not specifically describe known structure, material or method.
In whole instructions, " embodiment ", " embodiment ", " example " or mentioning of " example " are meaned: special characteristic, structure or characteristic in conjunction with this embodiment or example description are comprised at least one embodiment of the present invention.Therefore, differ and establish a capital the same embodiment of finger or example in each local phrase " in one embodiment ", " in an embodiment ", " example " or " example " occurring of whole instructions.In addition, can with any suitable combination and/or sub-portfolio by specific feature, structure or property combination in one or more embodiment or example.In addition, it should be understood by one skilled in the art that term "and/or" used herein comprises any and all combinations of one or more relevant projects of listing.
For the weak point that only uses the physical attribute information that is examined object in luggage to carry out safety inspection of the prior art, embodiments of the invention have proposed a kind of method in CT imaging system, luggage being checked.Utilize CT imaging system to obtain after the layer data that is examined luggage, generate from the layer data that is examined luggage the three-dimensional data that is examined at least one object luggage.Then calculate first depth projection image, second depth projection image and the three depth projection image of object in three directions based on three-dimensional data, wherein the projecting direction of the projecting direction of the 3rd depth projection image and the first and second depth projection images is orthogonal.Next, calculate first, second, and third depth projection image measure of symmetry value separately, similarity measurement value and dutycycle and depth-width ratio between any two.At least generate the parameters for shape characteristic of described inspected object based on measure of symmetry value separately of the first to the 3rd depth projection image, similarity measurement value between any two and dutycycle and depth-width ratio.Utilize the sorter based on parameters for shape characteristic to classify to described parameters for shape characteristic, the measure word that obtains the shape that embodies described object is described.Output at least comprises the semantic description that the described measure word of described object is described.Like this, data by the object to the acquisition of CT imaging system are processed the shape facility that has obtained object, and the mode with its semantic description is exported, make figure inspection person can obtain being examined intuitively, exactly the specific descriptions of object in luggage, thereby reduced loss.
According to another embodiment of the present invention, in order to reduce loss, provide a kind of method that shows object in CT imaging system.Be examined after the layer data of luggage utilizing CT imaging system to obtain, generate from layer data the three-dimensional data that is examined each object luggage.Then,, for each object, determine the semantic description of the measure word description that at least comprises described object based on three-dimensional data.Receive the selection of user to certain object, in showing the 3-D view of selected object, present the semantic description of this object.Like this, in the time being examined luggage and checking by CT imaging device, not only on screen, output is examined the image of object in luggage, and exports its semantic description for the selected object of figure inspection person, thereby present intuitively the description of object, reduced loss.
According to another embodiment of the present invention, in order to extract more exactly the shape facility that is examined object in luggage, embodiments of the invention provide a kind of in CT imaging system, create be examined luggage in the method for three-dimensional model of object.Utilize this CT imaging system to obtain after the layer data that is examined luggage, described layer data is carried out to interpolation, be examined the three-dimensional data of luggage described in generation.Then the described three-dimensional data that is examined luggage is carried out without supervised segmentation, obtain multiple regions of cutting apart, next contour surface extraction is carried out in multiple regions of cutting apart, obtain corresponding contour surface.Then contour surface is carried out to three-dimensional surface and cut apart, form the three-dimensional model of each object.The three-dimensional model that is examined object in luggage obtaining like this can be described being examined the three-dimensional surface of object in luggage comparatively exactly, for the extraction of follow-up three-dimensional shape features provides good basis, therefore can improve the accuracy rate of safety inspection.
Fig. 1 is according to the structural representation of the CT equipment of embodiment of the present invention.As shown in Figure 1, comprise according to the CT equipment of present embodiment: frame 20, load carrier 40, controller 50, computer data processor 60 etc.Frame 20 comprises sends the radiographic source 10 checking with X ray, such as X-ray machine, and detection and harvester 30.Load carrier 40 carryings are examined the scanning area of luggage 70 through radiographic source 10 and detection and the harvester 30 of frame 20, frame 20 is rotated around the working direction that is examined luggage 70 simultaneously, thereby the ray being sent by radiographic source 10 can see through and be examined luggage 70, carries out CT scan to being examined luggage 70.Detection and harvester 30 are for example detector and the data acquisition units with integral module structure, for example flat panel detector, for surveying the ray of the tested liquid article of transmission, obtain simulating signal, and convert simulating signal to digital signal, thereby output is examined the data for projection of luggage 70 for X ray.Controller 50 is for controlling the various piece synchronous working of whole system.Computer data processor 60 is used for processing the data that gathered by data acquisition unit, data is processed and is rebuild, Output rusults.
As shown in Figure 1, radiographic source 10 is placed in the side that can place tested object, and detection and harvester 30 are placed in the opposite side that is examined luggage 70, comprise detector and data acquisition unit, for obtaining the transmission data and/or the multi-angle projection data that are examined luggage 70.Data acquisition unit comprises data amplification wave-shaping circuit, and it can work in (electric current) integral way or pulse (counting) mode.Survey and be connected with controller 50 and computer data processor 60 with the data output cable of harvester 30, according to trigger command, the data of collection are stored in computer data processor 60.
Fig. 2 shows the structured flowchart of computer data processor 60 as shown in Figure 1.As shown in Figure 2, the data that data acquisition unit gathers are stored in storer 61 by interface unit 68 and bus 64.In ROM (read-only memory) (ROM) 62, store configuration information and the program of computer data processor.Random access memory (RAM) 63 is for keeping in various data in processor 66 courses of work.In addition, in storer 61, also store the computer program for carrying out data processing.Internal bus 64 connects above-mentioned storer 61, ROM (read-only memory) 62, random access memory 63, input media 65, processor 66, display device 67 and interface unit 68.
After the operational order of inputting by the input media 65 such as keyboard and mouse user, the instruction code instructs processor 66 of computer program is carried out predetermined data processing algorithm, after obtaining data processed result, be presented in the display device 67 such as LCD display, or the direct formal output result with hard copy such as printing.
Fig. 3 shows according to the structured flowchart of the controller of embodiment of the present invention.As shown in Figure 3, controller 50 comprises: control module 51, according to the instruction from computing machine 60, control radiographic source 10, load carrier 40 and detection and harvester 30; Trigger pip generation unit 52, for producing the trigger command of the action that is used for triggering radiographic source 10, detection and harvester 30 and load carrier 40 under the control of control module; The first driving arrangement 53, it drives load carrier 40 to transmit at the trigger command producing under the control of control module 51 according to trigger pip generation unit 52 and is examined luggage 70; The second driving arrangement 54, the trigger command frame 20 that it produces under the control of control module 51 according to trigger pip generation unit 52 is rotated.
Survey and the data for projection that obtains of harvester 30 is stored in and in computing machine 60, carries out CT tomographic image reconstructing, thereby acquisition is examined the faultage image data of luggage 70.Then computing machine 60 is for example extracted and is examined the 3D shape parameter of at least one object luggage 70 from faultage image data by executive software, and then carries out safety inspection.According to other embodiment, above-mentioned CT imaging system can be also double-energy CT system, namely the x-ray source 10 of frame 20 can send high energy and two kinds of rays of low energy, detection and harvester 30 detect after the data for projection under different-energy level, carry out dual intensity CT reconstruction by computer data processor 60, obtain the equivalent atom ordinal sum equivalent electron density data of each tomography that is examined luggage 70.
Fig. 4 shows according to the schematic diagram of the definition at each visual angle in the method for the embodiment of the present invention.Fig. 5 is the process flow diagram of describing according to the method in CT imaging system, luggage being checked.At step S51, utilize CT imaging system to obtain the layer data that is examined luggage.The for example CT equipment based on above-mentioned or other CT equipment carry out dual intensity CT examination to being examined luggage, obtain layer data, and the layer data here generally includes Fault density diagram data and tomography atomic number diagram data.For example, but in other embodiment, in the situation of monoenergetic CT, what obtain is linear attenuation coefficient view data.
At step S52, generate from layer data the three-dimensional data that is examined at least one object luggage.For example, layer data is carried out to interlayer interpolation, thereby obtain being examined the three-dimensional data of luggage.For another example, obtaining, after DECT density map under a series of continuous tomographies, atomic density figure, carrying out respectively three-dimensional interpolation to both, making the resolution of image in tomography, between tomography consistent.The known algorithm of three-dimensional interpolation is more, if business is by software I ntel IPP (Intel Integrated Performance Primitives) function library, open source software Kitware VTK (Visualization Toolkit) function library, all provides this function.After interpolation, two-dimentional layer data is converted to three-dimensional data.
At step S53, calculate first depth projection image, second depth projection image and the three depth projection image of described object in three directions based on described three-dimensional data, wherein the projecting direction of the projecting direction of the 3rd depth projection image and the first and second depth projection images is orthogonal.According to another embodiment, the projecting direction of the first depth projection image and the second depth projection image is orthogonal (for example roughly orthogonal) as far as possible, approach respectively this project objects area maximum with minimum direction.
Depth projection Depth Buffer be also Z-Buffering, is the basic fundamental of Surface rendering.Hiding relation between judgment object, and the part of not blocking is shown on screen.This technology is the typical technology that current 3DOR uses, but often relates to dozens of projection, and complexity is higher.As shown in Figure 4, in the present embodiment, only use 3 depth projection figure.First projection is defined as I 1, its objective is that this projection of sentencing area maximum approaches it in order to obtain " front view ".As shown in XOY plane in figure bis-, projection is I 1.Second projection is defined as I 2, its objective is that this projection of sentencing area minimum approaches in order to obtain " vertical view ".As shown in XOZ plane in figure bis-, projection is I 2.In figure bis-, these two projecting directions are orthogonal, but in fact may not meet this condition, and therefore these two projecting direction angulations are also as one of feature.The 3rd projection is defined as I 3, its objective is in order to obtain " side view ".Obtaining I 1, I 2projecting direction after, to be orthogonal to their projecting direction projection again, can obtain I 3, as the projection on YOZ face in Fig. 4 is I 3.
It should be noted that X in Fig. 4, Y, Z direction can forward, back projection goes out 6 images.Due in three-dimensional surface cutting procedure, details is removed, so positive and negative two is very similar to projection.For reducing algorithm complex, only use 3 projections here.
For obtaining area maximum or minimum projection, can adopt the method for all anglecs of rotation of traversal to realize, but complexity is too high like this.Use for reference Rectilinearity algorithm herein, use genetic algorithm to estimate fast the first two projecting direction.
I 1～I 3the symmetry of image can reflect the self-similarity of object, is important shape facility.For the ease of calculating, herein by I 1～I 3carrying out PCA (Principal Component Analyze, principal component analysis (PCA)) alignment, two dimensional image is maximized in x axle divergence, is also that the up-down symmetry of image is the strongest.Below indication I 1～I 3refer to the image through registration process.
At step S54, calculate the first depth projection image, the second depth projection image and the 3rd depth projection image measure of symmetry value separately, similarity measurement value and dutycycle and depth-width ratio between any two.
In certain embodiments, extract I 1～I 3symmetry, similarity, dutycycle, the ratio of width to height be as one or more in shape facility or their combination in any, as parameters for shape characteristic between two.In addition, aforementioned I 1, I 2between projecting direction, angle has also reflected body form, also as one of characteristic parameter.Further, object volume reflection article size, also as one of feature.
If the gray scale span of depth projection image is between [0,1].Wherein gray-scale value 0 represents infinity, the distance of non-zero value representation dough sheet and observation, and more closely value is larger.The acquisition methods of above-mentioned feature can be:
I) ask I 1～I 3up-down symmetry f 1 s～f 3 s.If I 1～I 3spin upside down and obtain image I 1'～I 3', definable up-down symmetry f i sfor:
f i S＝∑|I i-I i′|/∑(I i＞0|I i′＞0)(1)
After spinning upside down take image and the average gray difference of original image ask for up-down symmetry as standard.
Ii) ask I 1, I 2, I 3dutycycle f i dwith depth-width ratio f i r
Depth projection image size is that viewport defines, and does not reflect thingness.Ask depth projection depth-width ratio, dutycycle after alignment, can describe preferably object macroscopic property.Ask I iouter encirclement rectangle frame, easily ask its depth-width ratio f i r.Add up therein more non-zero number of pixels, divided by surrounding frame area, obtain its dutycycle f i d.
Iii) ask I 1, I 2, I 3between similarity f between two i b.
At ii) in I 1, I 2encirclement frame, the image surrounding in frame is determined, obtain
Figure BDA00002664219800081
will
Figure BDA00002664219800082
zoom to and
Figure BDA00002664219800083
equally size, obtains will
Figure BDA00002664219800085
spin upside down and obtain
Figure BDA00002664219800086
now can obtain f 1 b
Figure BDA00002664219800087
for:
f 1 B = max ( ( Σ | I 1 R - I 2 R ′ | / Σ ( I 1 R > 0 | I 2 R ′ > 0 ) ) , ( Σ | I 1 R - I 2 R ′ ′ | / Σ ( I 1 R > 0 | I 2 R ′ ′ > 0 ) ) ) - - - ( 2 )
Similarity ask method similar with formula (3) in symmetry, difference is in image has passed through size normalization.And get f 1 bfor
Figure BDA00002664219800089
with
Figure BDA000026642198000810
in similarity larger one.In like manner, can obtain I 2, I 3between similarity f 2 d, also have I 3, I 1between similarity f 3 d.
Iv) in depth projection process, known projection I 1, I 2both direction, ask its angle theta as feature.The size of model volume V reflection object, also as feature.
By each shape facility parameter combination described in above-mentioned steps, form 14 dimension shape facility vector F:
F＝{f 1 S，f 2 S，f 3 S，f 1 B，f 2 B，f 3 B，f 1 D，f 2 D，f 3 D，f 1 R，f 2 R，f 3 R，θ，V}(3)
At step S55, described at least generating based on measure of symmetry value separately of the first to the 3rd depth projection image, similarity measurement value between any two and dutycycle and depth-width ratio, be examined the parameters for shape characteristic of object in luggage.For example, in certain embodiments, based on above-mentioned from i) to iv) symmetry value, similarity, dutycycle and the depth-width ratio and the projection I that calculate 1and I 2one or more in the angle of both direction forms parameters for shape characteristic.
At step S56, utilize the sorter based on parameters for shape characteristic to classify to described parameters for shape characteristic, the measure word that obtains the shape that embodies described object is described.
Obtaining after eigenvector F, the process of structural classification device meets pattern-recognition general process, can use various dissimilar sorters, as linear classifier, support vector machine, decision tree, neural network, integrated classifier etc.After training, can realize the Shape Classification identification to unknown object.Embodiment adopts RF (Random Forest, random forest) to realize sorter.Many well known function storehouse comprises RF algorithm, as Open-Source Tools Opencv realizes function, repeats no more its process herein.
It should be noted that, on training set, by manually sentencing figure, the object obtaining in the 5th step need to be labeled as " bag, sheet, piece, bottle, tank, pipe, root, bag, box, individual " one of them.Here the difference of these predicates of simple declaration Chang Yuan.
" bag " refers to flat packing, and depth-width ratio is its key character.Such as Soft Roll milk, flat packed homogeneous foodstuff article etc.;
" sheet " refers to the object that thickness is very low, and depth-width ratio is its key character.Thin book, case and bag filling material, cutter are all in this scope;
" piece " refers to the object that similarity is lower, dutycycle is lower, such as the homogeneous object of plastic bag, will form " piece " if not the words of flat packing;
" bottle " refers to the article of similar mineral water bottle, and master, lateral projection's similarity, dutycycle, depth-width ratio are all its key characters;
" tank " refers to similar canned article, similar with bottle, but dutycycle, depth-width ratio are larger;
" root " refers to longer object, and depth-width ratio is its key character.Such as sausage, timber, iron pipe, all in this scope;
" pipe " is shorter than " root ", and the symmetric object having had, such as similar mildy wash, glue etc.;
" box " referred to certain thickness, and rectangle article are larger than " piece " dutycycle.Dutycycle, depth-width ratio are its principal characters, such as soap, many cosmetics, food have similar characteristics;
" bag " refers to larger object, and volume is its key character.Such as computing machine, very large very thick book, object larger, that can be judged as other shape is not at this type of;
" individual " is general reference " other " object.
Can see above-mentioned mode classification and general understanding difference to some extent.Than cup as shown in Figure 4, it may be " tank " that above predication word limits.Definition is for the concrete application contacts of safety check like this, such as solid explosive, generally can be with the form appearance of " bag ", " sheet ", " piece ", and liquid is take " bottle ", " tank ", " pipe " as main, and control apparatus " sheet ", " root " form are more.Other several as " bag ", " box ", " individual " are supplementary that Common Shape is done.
At step S57, output at least comprises the semantic description that the described measure word of described object is described.
In obtaining being examined luggage after the semantic description of each object, can be in several ways and user interactions.Such as directly show contour of object, call user's attention in result; Or in the time that user clicks, on screen, extract object and show descriptor, facilitating user further to understand and mark object.In addition, in specific occasion, object semanteme is limited, highlight the object that meets certain semantic, can reduce figure inspection person labour intensity, increase work efficiency.
Know position, the weight of object, known again the shape of object, so only need again statistical average atomic number and electron density (or linear attenuation coefficient) in monoenergetic CT situation can complete description.Afterwards, each predicate information all obtains, is arranged and obtains i.e. " shape+weight+density+atomic number+position " of object semantic description
Fig. 6 describes the process flow diagram that shows according to another embodiment of the present invention the method for object in CT imaging system.According to this embodiment, by automatic detection and description, realize the automatic auxiliary detection that is examined object in luggage.Object representation result is the necessary complement to manual detection, is also a kind of means of strengthening man-machine interaction, in undetected this major issue of minimizing, has very strong using value.
At step S61, utilize CT imaging system to obtain the layer data that is examined luggage.
At step S62, generate from described layer data the three-dimensional data that is examined each object luggage.Then,, at step S63, for each object, determine the semantic description of the described measure word description that at least comprises described object based on described three-dimensional data.
At step S64, receive the selection of user to certain object, in showing the 3-D view of selected object, present the semantic description of this object.
For example, all objects position detecting is labeled in display window, use the instrument chosen positions such as mouse within the scope of object during as figure inspection person, shows the semantic description of complete object.In addition, figure inspection person can choose object with instruments such as mouses, after choosing, can further mark in detail object, increases semantic description content.Can also make restriction to semantic description, only show the object that meets restriction.Be shaped as " bottle " and the object of weight more than 200 grams such as limiting only prompting, the position of suspicion object can represent in two-dimentional, 3-D view, and auxiliary view inspection person sentences figure.In addition, object can highlightedly show when selected, also can shield other all the elements, only shows object content.Alternatively, some restrictions of above-described embodiment are strengthened, such as intensive aspect data threshold limits, body form restriction, be can be used as certain objects as the automatic detection of explosive, contraband goods.
In other embodiments, produce and be examined the embodiment that the process of the semantic description of each object in luggage can be described with reference to upper combination Fig. 5.
According to embodiments of the invention, before carrying out depth projection, can also create the three-dimensional model that is examined object in luggage, further to extract shape facility and to carry out safety inspection.Fig. 7 be describe according to another embodiment of the present invention in CT imaging system, create be examined luggage in the process flow diagram of method of three-dimensional model of object.
As shown in Figure 7, at step S71, utilize CT imaging system to obtain the layer data that is examined luggage.At step S72, layer data is carried out to interpolation, generate the three-dimensional data that is examined luggage.For example, in dual intensity situation, three-dimensional data comprises density volume data and atomic number volume data.In monoenergetic situation, three-dimensional data comprises linear attenuation coefficient.
Obtaining, after DECT density map under a series of continuous tomographies, atomic density figure, carrying out respectively three-dimensional interpolation to both, making the resolution of image in tomography, between tomography consistent.The known algorithm of three-dimensional interpolation is more, if business is by software I ntel IPP (Intel Integrated Performance Primitives) function library, open source software Kitware VTK (Visualization Toolkit) function library, all provides this function.After interpolation, two-dimentional layer data is converted to three-dimensional data.In the situation of below not refering in particular to, described " volume data " comprises density volume data and atomic number volume data.
Secondly, volume data is carried out to threshold value restriction, remove the interference of the unconcerned foreign material of application such as article such as clothes.In concrete application, this step can be omitted, but calculated amount can increase, and " object " fruiting quantities obtaining can be a lot, cause result poor availability.
Afterwards, use three-dimensional bilateral filtering (bilateral filter) to carry out volume data filtering.Embodiment uses fast algorithm, also can use ITK (Insight Segmentation and Registration Toolkit) function library to realize.
At step S73, three-dimensional data is carried out without supervised segmentation, obtain multiple regions of cutting apart.
For two-dimentional partitioning algorithm, often cut apart based on realizations such as 4/8 neighborhood, gradient informations, need relevant treatment to expand to three-dimensional herein, such as 4 neighborhoods expand to 6 neighborhoods; Secondly, cutting apart related is density, courtyard ordinal number two parts volume data, can take both weighted sums, or each voxel represents with two-dimensional vector, obtains unified segmentation result; Have again, cut apart the effect that need to reach less divided.Preferably, we use Statistical Region Merging (SRM) algorithm, and are expanded to 3D processing and realize object.SRM is one merging partitioning algorithm from bottom to top, and the expansion that embodiment takes comprises:
1) atomic number, density are connected to vector, the each voxel of volume data is two-dimentional variable.Difference Vector Mode value with two vectors replaces gray scale difference;
2) replace two-dimensional gradient with three-dimensional gradient; With area pixel area in the volume replacement two dimension of region voxel;
Through above-mentioned processing, can realize DECT data without supervised segmentation.SRM segmentation result complexity is limited by complexity parameter in addition.Lower complexity value is set and can reaches less divided effect.
At step S74, contour surface extraction is carried out in multiple regions of cutting apart, obtain corresponding contour surface.
Each cut zone to step S73 gained is carried out contour surface extraction, can obtain corresponding contour surface.Use in an embodiment Marching Cubes algorithm.
At step S75, contour surface is carried out to three-dimensional surface and cut apart, to form the three-dimensional model of each object.
What obtain due to step S73 step is less divided result, multiple material characteristics are similar, position closely connected object cannot separate.Therefore need by surface segmentation refinement three-dimensional segmentation result.For example can use curved surface to cut apart (Mesh Segmentation) algorithm.Curved surface is divided into multiple convex surfaces.This algorithm, for there being supervise algorithm, need to be specified segmentation result number.In the time of practical application, can by similar K-Means cluster without supervision improve thinking, first calculate or iteration obtain cutting apart number.But through our experiment, the effect that similar approach is difficult to obtain, therefore we set that to cut apart number be 10.For 10 segmentation results, use for reference the protruding hypothesis of described star herein and carry out curved surface Merge.The center of supposing segmentation result curved surface A is a, and the center of curved surface B is b, if the line of a, b is in the 3rd step gained integral surface inside (or being less than certain threshold value at outside voxel proportion), A, B is coupled together.10 segmentation results are carried out to this connection procedure between two, can obtain final segmentation result.
According to embodiments of the invention, can also process the result after cutting apart, comprise and fill out hole, level and smooth, three steps of model restriction.The first two step is basic operation in graphics, can use open source software Kitware VTK (Visualization Toolkit) function library to realize, and repeats no more herein.Afterwards, by model voxelization, fill with density volume data value, add up surperficial area, volume, weight.Model limits to refer to and removes less object, comprises the less objects of value such as profile is long-pending, volume, weight.Limit reason and have two aspects.One, removes noise object, and result is more of practical significance; Its two, the local detail of a lot of objects is omitted, and makes next step shape recognition more accurate.The concrete threshold value that limits, with the resolution-dependent of DECT, according to actual conditions setting, such as weight can be set to 50 grams.
Above detailed description is by being used schematic diagram, process flow diagram and/or example, set forth the numerous embodiment of the method and apparatus of method, the display packing, the establishment three-dimensional model that check object.In the situation that this schematic diagram, process flow diagram and/or example comprise one or more functions and/or operation, it will be understood by those skilled in the art that each function in this schematic diagram, process flow diagram or example and/or operation can by various structures, hardware, software, firmware or in fact their combination in any come separately and/or jointly realize.In one embodiment, described in embodiments of the invention, some parts of theme can realize by special IC (ASIC), field programmable gate array (FPGA), digital signal processor (DSP) or other integrated forms.But, those skilled in the art will recognize that, some aspects of embodiment disclosed herein can realize in integrated circuit on the whole or partly equally, (be for example embodied as one or more computer programs of moving on one or more computing machine, be embodied as one or more programs of moving in one or more computer system), (be for example embodied as one or more programs of moving on one or more processors, be embodied as one or more programs of moving on one or more microprocessors), be embodied as firmware, or be embodied as in fact the combination in any of aforesaid way, and those skilled in the art are according to the disclosure, to possess design circuit and/or write software and/or the ability of firmware code.In addition, those skilled in the art will recognize that, described in the disclosure, the mechanism of theme can be distributed as the program product of various ways, and regardless of the actual particular type of signal bearing medium that is used for carrying out distribution, and the exemplary embodiment of theme is all suitable for described in the disclosure.The example of signal bearing medium includes but not limited to: recordable-type media, as floppy disk, hard disk drive, compact-disc (CD), digital universal disc (DVD), numerical tape, computer memory etc.; And transmission type media, for example, as numeral and/or analogue communication medium (, optical fiber cable, waveguide, wire communication link, wireless communication link etc.).
Although described the present invention with reference to several exemplary embodiments, should be appreciated that term used is explanation and exemplary and nonrestrictive term.Because can specifically implementing in a variety of forms, the present invention do not depart from spirit or the essence of invention, so be to be understood that, above-described embodiment is not limited to any aforesaid details, and explain widely in the spirit and scope that should limit in the claim of enclosing, therefore fall into whole variations in claim or its equivalent scope and remodeling and all should be the claim of enclosing and contain.

Claims (9)

1.一种在CT成像系统中创建被检查行李中物体的三维模型的方法，包括步骤：1. A method for creating a three-dimensional model of an object in checked luggage in a CT imaging system, comprising steps: 利用所述CT成像系统获取被检查行李的断层数据；Using the CT imaging system to obtain the tomographic data of the checked luggage; 对所述断层数据进行插值，生成所述被检查行李的三维体数据；Interpolating the tomographic data to generate three-dimensional volume data of the checked luggage; 对所述被检查行李的三维体数据进行无监督分割，得到多个分割的区域；performing unsupervised segmentation on the three-dimensional volume data of the checked luggage to obtain multiple segmented regions; 对所述多个分割的区域进行等值面提取，得到相应的等值面；performing isosurface extraction on the plurality of segmented regions to obtain corresponding isosurfaces; 对所述等值面进行三维表面分割，形成所述被检查行李中各个物体的三维模型。Performing three-dimensional surface segmentation on the isosurface to form a three-dimensional model of each object in the checked luggage. 2.如权利要1所述的方法，在对所述被检查行李的三维体数据进行无监督分割之前，还包括步骤：2. The method according to claim 1, before performing unsupervised segmentation on the three-dimensional volume data of the checked luggage, further comprising the steps of: 对所述被检查行李的三维体数据进行阈值限定，去掉杂物数据；Threshold limit the three-dimensional volume data of the baggage to be inspected, and remove the sundry data; 对所述被检查行李的三维体数据进行滤波。Filtering is performed on the three-dimensional volume data of the checked luggage. 3.如权利要求1所述的方法，对所述等值面进行三维表面分割的步骤包括：3. The method according to claim 1, the step of carrying out three-dimensional surface segmentation to the isosurface comprises: 将等值面分割成多个曲面；Divide the isosurface into multiple surfaces; 如果两个曲面的中心的连线在等值面内，则将两个曲面连接起来。Two surfaces are joined if the line connecting their centers lies within the isosurface. 4.如权利要求1所述的方法，还包括对三维表面分割后的结果进行填洞、平滑和模型限定处理。4. The method according to claim 1, further comprising performing hole filling, smoothing and model definition processing on the result of three-dimensional surface segmentation. 5.如权利要求1所述的方法，其中所述CT成像系统具体为双能CT成像系统，所述被检查行李的三维体数据包括电子密度体数据和原子序数体数据。5. The method according to claim 1, wherein the CT imaging system is specifically a dual-energy CT imaging system, and the three-dimensional volume data of the inspected luggage includes electron density volume data and atomic number volume data. 6.如权利要求1所述的方法，其中所述CT成像系统具有为单能CT成像系统，所述被检查行李的三维体数据包括线性衰减系数体数据。6. The method according to claim 1, wherein the CT imaging system is a single-energy CT imaging system, and the three-dimensional volume data of the checked luggage includes linear attenuation coefficient volume data. 7.一种在CT成像系统中创建被检查行李中物体的三维模型的设备，包括：7. A device for creating a three-dimensional model of an object in checked baggage in a CT imaging system, comprising: 利用所述CT成像系统获取被检查行李的断层数据的装置；A device for obtaining tomographic data of checked luggage by using the CT imaging system; 对所述断层数据进行插值，生成所述被检查行李的三维体数据的装置；A device for interpolating the tomographic data to generate three-dimensional volume data of the checked luggage; 对所述被检查行李的三维体数据进行无监督分割，得到多个分割的区域的装置；A device for unsupervised segmentation of the three-dimensional volume data of the checked baggage to obtain multiple segmented regions; 对所述多个分割的区域进行等值面提取，得到相应的等值面的装置；performing isosurface extraction on the multiple segmented regions to obtain corresponding isosurfaces; 对所述等值面进行三维表面分割，形成所述被检查行李中各个物体的三维模型的装置。A device for performing three-dimensional surface segmentation on the isosurface to form a three-dimensional model of each object in the checked luggage. 8.如权利要7所述的设备，还包括：8. The device of claim 7, further comprising: 对所述被检查行李的三维体数据进行阈值限定，去掉杂物数据的装置；A device for limiting the threshold value of the three-dimensional volume data of the checked luggage and removing the sundry data; 对所述被检查行李的三维体数据进行滤波的装置。A device for filtering the three-dimensional volume data of the checked luggage. 9.如权利要求7所述的设备，对所述等值面进行三维表面分割的装置包括：9. The apparatus according to claim 7, the means for carrying out three-dimensional surface segmentation to the isosurface comprises: 将等值面分割成多个曲面的装置；means for splitting isosurfaces into multiple surfaces; 如果两个曲面的中心的连线在等值面内，则将两个曲面连接起来的装置。A device that connects two surfaces if the line connecting their centers lies within the isosurface.
CN201210581858.2A 2012-12-27 2012-12-27 Threedimensional model creation method and equipment Active CN103903303B (en)

Priority Applications (3)

Application Number Priority Date Filing Date Title
CN201210581858.2A CN103903303B (en) 2012-12-27 2012-12-27 Threedimensional model creation method and equipment
PCT/CN2013/087662 WO2014101600A1 (en) 2012-12-27 2013-11-22 Method and device for creating three-dimensional model
US14/138,447 US9557436B2 (en) 2012-12-27 2013-12-23 3-dimensional model creation methods and apparatuses

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210581858.2A CN103903303B (en) 2012-12-27 2012-12-27 Threedimensional model creation method and equipment

Publications (2)

Publication Number Publication Date
CN103903303A true CN103903303A (en) 2014-07-02
CN103903303B CN103903303B (en) 2018-01-30

Family

ID=50994608

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210581858.2A Active CN103903303B (en) 2012-12-27 2012-12-27 Threedimensional model creation method and equipment

Country Status (3)

Country Link
US (1) US9557436B2 (en)
CN (1) CN103903303B (en)
WO (1) WO2014101600A1 (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106886054A (en) * 2017-04-13 2017-06-23 西安邮电大学 Dangerous material automatic identification equipment and method based on 3 D X-ray imaging
WO2019028721A1 (en) * 2017-08-10 2019-02-14 哈尔滨工业大学 Method for use in item recognition, apparatus, device, and security system
CN109374658A (en) * 2018-12-24 2019-02-22 电子科技大学 A neural network reconstruction tomography method for dual-view X-ray security inspection system
CN110726643A (en) * 2019-11-18 2020-01-24 辽宁机电职业技术学院 Laser detection system and detection method for diamond density test
CN111735735A (en) * 2020-06-11 2020-10-02 山东滨州烟草有限公司 A kind of intelligent cigarette package non-destructive identification method and identification device
CN113643360A (en) * 2020-05-11 2021-11-12 同方威视技术股份有限公司 Target object positioning method, apparatus, device, medium, and program product
CN113643361A (en) * 2020-05-11 2021-11-12 同方威视技术股份有限公司 Target area localization method, apparatus, apparatus, medium and program product
WO2023280210A1 (en) * 2021-07-07 2023-01-12 清华大学 Inspection system and method

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101433242B1 (en) * 2012-11-16 2014-08-25 경북대학교 산학협력단 Reduction surgical robot and method for driving control thereof
US9646411B2 (en) * 2015-04-02 2017-05-09 Hedronx Inc. Virtual three-dimensional model generation based on virtual hexahedron models
US9996772B2 (en) * 2016-04-28 2018-06-12 International Business Machines Corporation Detection of objects in images using region-based convolutional neural networks
US11559378B2 (en) * 2016-11-17 2023-01-24 James R. Glidewell Dental Ceramics, Inc. Scanning dental impressions
CN106526686B (en) * 2016-12-07 2019-05-07 同方威视技术股份有限公司 Spiral CT equipment and three-dimensional image reconstruction method
US11205103B2 (en) 2016-12-09 2021-12-21 The Research Foundation for the State University Semisupervised autoencoder for sentiment analysis
US11481961B2 (en) * 2018-10-02 2022-10-25 Sony Corporation Information processing apparatus and information processing method
US11540906B2 (en) 2019-06-25 2023-01-03 James R. Glidewell Dental Ceramics, Inc. Processing digital dental impression
US11534271B2 (en) 2019-06-25 2022-12-27 James R. Glidewell Dental Ceramics, Inc. Processing CT scan of dental impression
US11622843B2 (en) 2019-06-25 2023-04-11 James R. Glidewell Dental Ceramics, Inc. Processing digital dental impression
JP7250331B2 (en) * 2019-07-05 2023-04-03 株式会社イシダ Image generation device, inspection device and learning device
CN110675488B (en) * 2019-09-24 2023-02-28 电子科技大学 Construction method of the modeling system of creative 3D voxel model based on deep learning
US11544846B2 (en) 2020-08-27 2023-01-03 James R. Glidewell Dental Ceramics, Inc. Out-of-view CT scan detection
GB2608187B (en) * 2021-06-25 2024-06-19 Smiths Detection France S A S X-ray inspection system and control architecture for an X-ray inspection system
CN114373060B (en) * 2022-03-23 2022-06-28 超节点创新科技(深圳)有限公司 Luggage model generation method and equipment

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1352781A (en) * 1999-03-18 2002-06-05 纽约州立大学研究基金会 System and method for performing a three-dimenional virtual segmentation and examination
CN101551906A (en) * 2009-05-13 2009-10-07 西安电子科技大学 Extraction method of main blood vessels from abdominal CT images based on watershed of three-dimensional region
WO2011019456A1 (en) * 2009-06-26 2011-02-17 University Of South Florida Ct atlas of musculoskeletal anatomy to guide treatment of sarcoma
WO2011092594A3 (en) * 2010-02-01 2011-09-29 Superdimension, Ltd. Region-growing algorithm
CN102402788A (en) * 2011-12-22 2012-04-04 华南理工大学 A Segmentation Method of 3D Ultrasonic Image
CN102768699A (en) * 2012-06-14 2012-11-07 西安交通大学 Method for accurately reconstructing dissimilar material microcosmic finite element grid model on basis of CT (computed tomography) images

Family Cites Families (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5712926A (en) * 1994-10-20 1998-01-27 Eberhard; Jeffrey Wayne X-ray computed tomography (CT) system for detecting thin objects
US6026171A (en) * 1998-02-11 2000-02-15 Analogic Corporation Apparatus and method for detection of liquids in computed tomography data
US6035014A (en) * 1998-02-11 2000-03-07 Analogic Corporation Multiple-stage apparatus and method for detecting objects in computed tomography data
US6026143A (en) * 1998-02-11 2000-02-15 Analogic Corporation Apparatus and method for detecting sheet objects in computed tomography data
US6076400A (en) * 1998-02-11 2000-06-20 Analogic Corporation Apparatus and method for classifying objects in computed tomography data using density dependent mass thresholds
US6128365A (en) * 1998-02-11 2000-10-03 Analogic Corporation Apparatus and method for combining related objects in computed tomography data
US6078642A (en) * 1998-02-11 2000-06-20 Analogice Corporation Apparatus and method for density discrimination of objects in computed tomography data using multiple density ranges
US6272230B1 (en) * 1998-02-11 2001-08-07 Analogic Corporation Apparatus and method for optimizing detection of objects in computed tomography data
US6317509B1 (en) * 1998-02-11 2001-11-13 Analogic Corporation Computed tomography apparatus and method for classifying objects
US6108396A (en) * 1998-02-11 2000-08-22 Analogic Corporation Apparatus and method for correcting object density in computed tomography data
US6067366A (en) * 1998-02-11 2000-05-23 Analogic Corporation Apparatus and method for detecting objects in computed tomography data using erosion and dilation of objects
US6111974A (en) * 1998-02-11 2000-08-29 Analogic Corporation Apparatus and method for detecting sheet objects in computed tomography data
US6075871A (en) * 1998-02-11 2000-06-13 Analogic Corporation Apparatus and method for eroding objects in computed tomography data
US6195444B1 (en) * 1999-01-12 2001-02-27 Analogic Corporation Apparatus and method for detecting concealed objects in computed tomography data
WO2001078005A2 (en) * 2000-04-11 2001-10-18 Cornell Research Foundation, Inc. System and method for three-dimensional image rendering and analysis
JP3442346B2 (en) * 2000-06-01 2003-09-02 カナガワ アンド カンパニー株式会社 Image forming apparatus and image forming method using the same
WO2003024184A2 (en) * 2001-09-14 2003-03-27 Cornell Research Foundation, Inc. System, method and apparatus for small pulmonary nodule computer aided diagnosis from computed tomography scans
US7062009B2 (en) * 2002-09-12 2006-06-13 Analogic Corporation Helical interpolation for an asymmetric multi-slice scanner
US8045770B2 (en) * 2003-03-24 2011-10-25 Cornell Research Foundation, Inc. System and method for three-dimensional image rendering and analysis
US7277577B2 (en) * 2004-04-26 2007-10-02 Analogic Corporation Method and system for detecting threat objects using computed tomography images
US8059900B2 (en) * 2004-10-08 2011-11-15 General Electric Company Method and apparatus to facilitate visualization and detection of anatomical shapes using post-processing of 3D shape filtering
EP1971850A2 (en) * 2005-12-12 2008-09-24 Reveal Imaging Techologies Displaced-ray ct inspection
US8244015B2 (en) * 2006-11-22 2012-08-14 General Electric Company Methods and apparatus for detecting aneurysm in vasculatures
CN102608135B (en) * 2007-10-05 2015-02-18 清华大学 Method and equipment for confirming CT (Computed Tomography) scanning position in dangerous goods inspection system
US8644578B1 (en) * 2008-04-25 2014-02-04 Stratovan Corporation Method and apparatus of identifying objects of interest using imaging scans
US8600149B2 (en) * 2008-08-25 2013-12-03 Telesecurity Sciences, Inc. Method and system for electronic inspection of baggage and cargo
CN101900694B (en) * 2009-05-27 2012-05-30 清华大学 System and method for dual-energy undersampling substance identification based on linear trajectory scanning
WO2013173574A1 (en) * 2012-05-16 2013-11-21 The Johns Hopkins University Imaging system and method for use of same to determine metric scale of imaged bodily anatomy

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1352781A (en) * 1999-03-18 2002-06-05 纽约州立大学研究基金会 System and method for performing a three-dimenional virtual segmentation and examination
CN101551906A (en) * 2009-05-13 2009-10-07 西安电子科技大学 Extraction method of main blood vessels from abdominal CT images based on watershed of three-dimensional region
WO2011019456A1 (en) * 2009-06-26 2011-02-17 University Of South Florida Ct atlas of musculoskeletal anatomy to guide treatment of sarcoma
WO2011092594A3 (en) * 2010-02-01 2011-09-29 Superdimension, Ltd. Region-growing algorithm
CN102402788A (en) * 2011-12-22 2012-04-04 华南理工大学 A Segmentation Method of 3D Ultrasonic Image
CN102768699A (en) * 2012-06-14 2012-11-07 西安交通大学 Method for accurately reconstructing dissimilar material microcosmic finite element grid model on basis of CT (computed tomography) images

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
MARIUSZ BAJGER 等: "FULL-BODY CT SEGMENTATION USING 3D EXTENSION OF TWO GRAPH-BASED METHODS: A FEASIBILITY STUDY", 《PROCEEDINGS OF THE IA STED INTERNATIONAL CONFERENCE SIGNAL PROCESSING, PATTERN RECOGNITION AND APPLICATIONS (SPPRA 2012)》 *
XIAOTAO WANG 等: "Remote Sensing Image Segmentation Based on Statistical Region Merging and Nonlinear Diffusion", 《2010 2ND INTERNATIONAL ASIA CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS》 *
吴万龙 等: "CT技术在安检领域的应用", 《CT 理论与应用研究》 *
韩成虎: "CT图像三维重建技术的研究与应用", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106886054A (en) * 2017-04-13 2017-06-23 西安邮电大学 Dangerous material automatic identification equipment and method based on 3 D X-ray imaging
WO2019028721A1 (en) * 2017-08-10 2019-02-14 哈尔滨工业大学 Method for use in item recognition, apparatus, device, and security system
CN109374658A (en) * 2018-12-24 2019-02-22 电子科技大学 A neural network reconstruction tomography method for dual-view X-ray security inspection system
CN109374658B (en) * 2018-12-24 2022-05-03 电子科技大学 Neural network reconstruction tomography method of double-view X-ray security inspection system
CN110726643A (en) * 2019-11-18 2020-01-24 辽宁机电职业技术学院 Laser detection system and detection method for diamond density test
CN113643360A (en) * 2020-05-11 2021-11-12 同方威视技术股份有限公司 Target object positioning method, apparatus, device, medium, and program product
CN113643361A (en) * 2020-05-11 2021-11-12 同方威视技术股份有限公司 Target area localization method, apparatus, apparatus, medium and program product
CN111735735A (en) * 2020-06-11 2020-10-02 山东滨州烟草有限公司 A kind of intelligent cigarette package non-destructive identification method and identification device
WO2023280210A1 (en) * 2021-07-07 2023-01-12 清华大学 Inspection system and method

Also Published As

Publication number Publication date
WO2014101600A1 (en) 2014-07-03
CN103903303B (en) 2018-01-30
US20140185742A1 (en) 2014-07-03
US9557436B2 (en) 2017-01-31

Similar Documents

Publication Publication Date Title
CN103903303A (en) Three-dimensional model establishing method and device
CN103901489A (en) Method and device for inspecting object, and a display method
CN103900503A (en) Shape characteristic extraction method, safety inspection method and device
RU2599277C1 (en) Computed tomography system for inspection and corresponding method
CN101358936B (en) Method and system for discriminating material by double-perspective multi energy transmission image
EP2988117B1 (en) X-ray diffraction imaging system with signal aggregation across voxels containing objects and method of operating the same
CN116229195B (en) Method for online training of radiation image recognition model, radiation image recognition method and device
KR20250137573A (en) Method and device for separating a target object within a three-dimensional CT image, and a security inspection CT system
HK1195820A (en) 3-dimensional model creation methods and apparatuses
HK1195820B (en) 3-dimensional model creation methods and apparatuses
HK1195943A (en) Methods for detecting objects, display methods and apparatuses
HK1195943B (en) Methods for detecting objects, display methods and apparatuses
CN115452870A (en) System and method for identifying explosives
CN115508390A (en) Explosive identification method
Chen Data Decomposition Techniques for Visualization
HK1195805B (en) Methods for extracting shape feature, inspection methods and apparatuses
Neelakantan et al. Applied Computing and Geosciences
HK1195805A (en) Methods for extracting shape feature, inspection methods and apparatuses
HK1218157B (en) Ct system for security check and method thereof

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
REG Reference to a national code

Ref country code: HK

Ref legal event code: DE

Ref document number: 1195820

Country of ref document: HK

GR01 Patent grant
GR01 Patent grant
REG Reference to a national code

Ref country code: HK

Ref legal event code: GR

Ref document number: 1195820

Country of ref document: HK